{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/langevin-gradient-parallel-tempering-for","title":"Langevin-gradient parallel tempering for Bayesian neural learning","arxiv_id":"1811.04343","date":"2018-11-11","proceeding":null,"authors":["Rohitash Chandra","Konark Jain","Ratneel V. Deo","Sally Cripps"],"abstract":"Bayesian neural learning feature a rigorous approach to estimation and\nuncertainty quantification via the posterior distribution of weights that\nrepresent knowledge of the neural network. This not only provides point\nestimates of optimal set of weights but also the ability to quantify\nuncertainty in decision making using the posterior distribution. Markov chain\nMonte Carlo (MCMC) techniques are typically used to obtain sample-based\nestimates of the posterior distribution. However, these techniques face\nchallenges in convergence and scalability, particularly in settings with large\ndatasets and network architectures. This paper address these challenges in two\nways. First, parallel tempering is used used to explore multiple modes of the\nposterior distribution and implemented in multi-core computing architecture.\nSecond, we make within-chain sampling schemes more efficient by using Langevin\ngradient information in forming Metropolis-Hastings proposal distributions. We\ndemonstrate the techniques using time series prediction and pattern\nclassification applications. The results show that the method not only improves\nthe computational time, but provides better prediction or decision making\ncapabilities when compared to related methods.","url_abs":"http://arxiv.org/abs/1811.04343v1","url_pdf":"http://arxiv.org/pdf/1811.04343v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"langevin-gradient-parallel-tempering-for","repo_url":"https://github.com/sydney-machine-learning/surrogate-assisted-parallel-tempering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-prediction","task_name":"Time Series Prediction"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.04343","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}